AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

AnnData Single-Cell Data Handler

A skill for creating, reading/writing, concatenating and scaling AnnData (.h5ad, Zarr) objects using the current 0.13.x API.

Data & AnalyticsIntermediate★ 56,496⑂ 4,969AI score 9/10Last updated: Nov 2, 2026

What it does

  • Teaches and applies the AnnData layout correctly: X, obs, var, layers, obsm/varm, obsp/varp, uns, raw.
  • Handles I/O across h5ad, Zarr, CSV, MTX and Loom, plus backed (lazy) mode and remote stores.
  • Concatenates datasets with ad.concat (inner/outer joins, label/keys), distinguishes views vs copies, and converts strings to categoricals for memory savings.
  • Encodes 0.13 breaking changes: AnnData.concatenate() removed, prefer anndata.io, .X also appears as layers[None], Zarr v3 + sharding defaults, AnnLoader/Loom deprecated.
  • Supplies fixes for common failures: OOM, slow reads, and index-misalignment when adding obs columns.

Who it's for

  • Researchers and analysts working in the scverse stack (scanpy, scvi-tools, muon) on single-cell or spatial omics.
  • Bioinformatics engineers who must process tens-of-GB h5ad files within RAM limits.
  • Anyone migrating older AnnData example code to the current API.

Examples

  1. "Merge batch1–batch3.h5ad with batch labels using an inner join" → produces ad.concat(..., label='batch', keys=[...]) plus post-merge sanity checks.
  2. "Pull only cells with quality_score > 0.8 out of a 100GB h5ad" → opens with backed='r', filters on metadata, materializes with to_memory(), then closes the file.
  3. "Keep raw counts while subsetting to 2000 highly variable genes" → stores layers['counts'], snapshots adata.raw, then applies the HVG subset in the right order.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/anndata/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/anndata folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/anndata/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/anndata ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/anndata ~/.claude/skills/
  5. Verify the bundled references/ docs came along: ls ~/.claude/skills/anndata
  6. Install the library in a Python 3.12+ environment: uv pip install "anndata==0.13.4" (add lazy I/O with uv pip install "anndata[dask,lazy]==0.13.4").
  7. Restart Claude Code and test with a request like "concatenate these h5ad files" to confirm the skill triggers.
View source on GitHub ↗License: MIT